不兼容的形状均方误差

Question

我想用Keras训练一个RNN, X的形状是(4413, 71, 19)，而y的形状是(4413,2)

代码

model = Sequential()
model.add(LSTM(128, return_sequences=True, input_shape=(None,19)))
model.add(Dropout(.2))
model.add(BatchNormalization())
model.add(LSTM(128, return_sequences=True, input_shape=(None,19)))
model.add(Dropout(.2))
model.add(BatchNormalization())
model.add(LSTM(128, return_sequences=True, input_shape=(None,19)))
model.add(Dropout(.2))
model.add(BatchNormalization())
model.add(Dense(32, activation='relu'))
model.add(Dropout(.2))
model.add(Dense(2, activation='softmax'))
model.compile(optimizer='adam', loss='mean_squared_error', metrics=['mean_squared_error'])

当我拟合模型时，我得到了这个错误，似乎损失函数不能拟合这种数据

Incompatible shapes: [64,2] vs. [64,71,2]
[[{{node mean_squared_error/SquaredDifference}}]] [Op:__inference_train_function_157671]

Answer 1

尝试将最后一层LSTM的return_sequences参数设置为False:

model = Sequential()
model.add(LSTM(128, return_sequences=True, input_shape=(None,19)))
model.add(Dropout(.2))
model.add(BatchNormalization())
model.add(LSTM(128, return_sequences=True))
model.add(Dropout(.2))
model.add(BatchNormalization())
model.add(LSTM(128, return_sequences=False))
model.add(Dropout(.2))
model.add(BatchNormalization())
model.add(Dense(32, activation='relu'))
model.add(Dropout(.2))
model.add(Dense(2, activation='linear'))
model.compile(optimizer='adam', loss='mean_squared_error', metrics=['mean_squared_error'])

我还将输出层中的激活函数更改为linear，因为softmax层在您的情况下没有多大意义。也可以参考这个答案